arXiv AI June 3, 2026 By Krishnapriya Vishnubhotla, Hillary Dawkins, Isar Nejadgholi, Svetlana Kiritchenko

Safety Measurements for Fine-tuned LLMs Should be Grounded in Capability

arXiv:2606. 03648v1 Announce Type: cross Abstract: Adapting foundation large language models to a user's task or preferred style through fine-tuning can result in compromising the model's safety.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

6d ago

Making Your LLMs More Objective: Stabilizing LLM Safety Behavior Across Traits with Trait-Invariant Safety Tuning

arXiv:2608. 11705v1 Announce Type: new Abstract: Aligned large language models (LLMs) are expected to exhibit safety behavior based on the content of the user request: they should refuse unsafe requests and comply with safe ones.

By Lang Cao

llms efficiency safety

arXiv AI

Jun 30

The Heterogeneous Safety Impacts of Benign Multilingual Fine-Tuning

arXiv:2606. 28843v1 Announce Type: cross Abstract: Fine-tuning a large language model is a ubiquitous method for enhancing its capability on a specific downstream task.

By Will Hawkins, Kaivalya Rawal, Jonathan Rystr{\o}m, Stratis Tsirtsis, Zihao Fu, Greta Warren, Ryan Brown, Eoin Delaney, Sandra Wachter, Brent Mittelstadt, Chris Russell

llms fine-tuning safety

arXiv Machine Learning

Jun 11

AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin

arXiv:2506. 08473v4 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) improves performance but introduces critical safety vulnerabilities: even minimal harmful data can severely compromise safety measures.

By Shuo Yang, Qihui Zhang, Yuyang Liu, Xiaojun Jia, Kunpeng Ning, Jiayu Yao, Jigang Wang, Hailiang Dai, Yibing Song, Li Yuan

llms fine-tuning safety

arXiv Machine Learning

Jul 14

Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs

arXiv:2607. 09697v1 Announce Type: new Abstract: Existing safety mechanisms for multimodal large language models (MLLMs) face a fundamental trade-off between safety and utility.

By Jiayi Li, Kun Zhan

llms fine-tuning multimodal safety

arXiv AI

Jun 30

CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models

arXiv:2501. 14940v4 Announce Type: replace-cross Abstract: Aligning large language models (LLMs) with human values is essential for their safe deployment and widespread adoption.

By Guangzhi Sun, Xiao Zhan, Shutong Feng, Philip C. Woodland, Jose Such

llms benchmarks safety

arXiv AI

Jun 2

The Refusal--Compliance Tradeoff: A Large-Scale Safety Behavior Audit of Large Language Models

arXiv:2605. 05427v2 Announce Type: replace Abstract: Refusal rates are a poor proxy for LLM safety, i.

By Alif Al Hasan, Sumon Biswas

llms benchmarks safety

Related stories

Making Your LLMs More Objective: Stabilizing LLM Safety Behavior Across Traits with Trait-Invariant Safety Tuning

The Heterogeneous Safety Impacts of Benign Multilingual Fine-Tuning

AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin

Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs

CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models

The Refusal--Compliance Tradeoff: A Large-Scale Safety Behavior Audit of Large Language Models